Vulnerability  ·  2026-04-22

Anthropic's Mythos AI Model Accessed by Unauthorized Users in Security Breach

VulnerabilityHigh impactGlobal
A small group of unauthorized users gained access to Anthropic's Mythos AI model through a private online forum on the same day the company announced limited enterprise testing.
Unauthorized access through unspecified means to a restricted AI model designed for cybersecurity research and vulnerability discovery.
Anthropic Mythos AI model, described as capable of enabling dangerous cyberattacks and finding vulnerabilities at expert researcher level.
Anthropic is restricting access to the model to help governments, tech giants, and banks secure their systems ahead of broader release.
Sources
Bloomberg
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →